Dissertation > Excellent graduate degree dissertation topics show

Research and Application of Information Extraction -based the multidimensional semantics Internet drugs

Author: GuZuoLing
Tutor: LiYinSheng
School: Fudan University
Course: Computer Software and Theory
Keywords: Multi-dimensional Semantic Dictionary Structural Semantic Entropy Web Information Extraction XPath
CLC: TP393.09
Type: Master's thesis
Year: 2011
Downloads: 25
Quote: 0
Read: Download Dissertation

Abstract


In recent years, Internet medicine market is expanding rapidly with the development of E-commerce but hidden danger which comes along with it also becomes more and more serious. The Internet being flooded by non-standard or even fake medicine information, regulatory authorities need an advanced Web medicine information extraction and monitoring method to reinforce the supervision over this market. For this purpose, Fudan and Tsinghua University established a joint program of "System Research and Development on Web Medicine Information Management and Intelligent Monitoring Method" and deeply probed into related methods and achieved outstanding results.Traditional Web information extraction methods usually require high manual intervention and lack of adaptability or flexibility, which made recognition of new information sources hard. This paper proposed a multi-dimensional-semantics-based Web medicine information extraction method after researching on related works, which describes semantics related to Web medicine information extraction from multiple dimensions, thus can overcome the heterogeneity and keep the common characteristics of the content and structure from different websites. It also utilizes structural-semantic-entropy to precisely recognize and locate medicine information in web pages. The design and implementation of the multi-dimensional semantic dictionary and the whole information extraction system are discussed in detail in this paper and the method is verified by experiments. Results show that the method is able to greatly reduce manual intervention, yield high precision and recall, and automatically identify medicine information from unknown websites with high flexibility and adaptability.The application of the Web medicine information extraction method proposed in this paper can provide information support for accurate, comprehensive, real-time and automatic medicine information monitoring and intelligent monitoring mechanism for regulatory authorities, which is significant for market regularity and medicine safety.

Related Dissertations

  1. XPath Querying Technology Research Based Structure Index of XML Data Stream,TP311.13
  2. The Model Construction and Optimization of XML Document Filter System,TP391.1
  3. Ontology-based Web information extraction field of tourism,TP391.11
  4. Research on XML Data Query Optimization Technique,TP311.10
  5. Web Mining Research and Implementation of information collection technology,TP274.2
  6. Semi-structured Web information extraction technology and its application,TP393.09
  7. The Application of Xpath and XSLT in Querying XML Document,TP311.13
  8. Based on XML and XSLT Research and Design of Web Information Extraction,TP393.09
  9. SVM-based Web information extraction technology research,TP393.09
  10. XML and Its Application in Manufacture Information System,TP399
  11. Research on Web Information Extraction in Information Integration,TP393.09
  12. Schema-based XML query rewrite and indexing techniques,TP312.2
  13. Data Integration in ERP and E-Commerce Based on XML,TP311.13
  14. Research on the Transformation from RBAC-Featured Data Stored in Database to XACML Policy,TP311.13
  15. Network environment XPath query set redundancy removal of,TP311.13
  16. Research on Predicate-based Query Processing of XML Streams,TP312.2
  17. Application of Web Information Extraction in Commercial Bank Credit Risks Supervisory System,TP319
  18. Research of Web Information Extraction Based on XML,TP391.1
  19. Web-oriented book information extraction methods and implementation,TP311.52
  20. Development of human technology - based web content extraction system,TP393.092

CLC: > Industrial Technology > Automation technology,computer technology > Computing technology,computer technology > Computer applications > Computer network > General issues > The application of computer network
© 2012 www.DissertationTopic.Net  Mobile